Update README.md

added WizardLM_evol_instruct_V2_196k details and upstream links

README.md

@@ -1,10 +1,19 @@
 ---
 inference: false
+datasets:
+- WizardLM/WizardLM_evol_instruct_V2_196k
 ---
 # Model Card for Model ID
 
 
-This is exl2 5.53bpw quant of ToolLLaMA-2-7b version model introduced in [ToolBench](https://github.com/OpenBMB/ToolBench).
+This is exl2 5.53bpw quant of Vicuna, specifically https://huggingface.co/lmsys/vicuna-13b-v1.5-16k
+
+More notes on the original model can be found here [lmSys page](https://github.com/lm-sys/FastChat/blob/main/docs/vicuna_weights_version.md).
+
+`python convert.py -i C:\webui\models\deepseek-ai_deepseek-coder-6.7b-instruct 
+-o C:\webui\models\Processed -nr -m deepseek-ai_deepseek-coder-6.7b-instruct_measurement.json 
+-b 2.4 -gr 50 -c "C:\webui\repositories\exllamav2\WizardLM_evol_instruct_V2_196k_0000.parquet" 
+-cf deepseek-ai_deepseek-coder-6.7b-instruct-exl2-2.4bpw -ss 4000`
 
 ## Original Model Details